-------------------------------------------------------------------------------
help for postrri
-------------------------------------------------------------------------------

Posterior Relative Risk

postrri , prior(#lb #ub) data(#rr #lb #ub) [ level(#) lprior(#) ldata(#) format(%fmt) ]

Description

postrri provides an easy way to do Bayesian analyses via inverse-variance (information) weighted averaging of the prior with the frequentist relative risk. It is an immediate command, see help immed. Options

prior(#lb #ub) specifies the confidence limits for the prior relative risk.

data(#rr #lb #ub) specifies the frequentist relative risk and confidence limits for the data.

level(#) specifies the confidence level for the posterior relative risk. The default is 95%.

lprior(#) specifies the probability for the Bayesian interval. The default is 95%.

ldata(#) specifies the confidence level for the frequentist interval. The default is 95%.

format(%fmt) specifies the display format for presenting numbers. format(%3.2f) is the default; see help format.

Examples

. postrri , prior(0.25 4) data(3.51 .80 15.4) . postrri , prior(0.25 4) data(3.51 .80 15.4) l(90) . postrri , prior(0.25 4) data(3.51 .80 15.4) l(99) . postrri , prior(0.25 4) data(3.51 .80 15.4) f(%4.3f) . postrri , prior(0.25 4) data(1.69 1.28 2.23)

Reference

Greenland S. (2006) Bayesian perspectives for epidemiologic research. I. Foundations and basic methods., International Journal of Epidemiology, 35:765-775. Authors

Nicola Orsini, Division of Nutritional Epidemiology, Institute of Environmental Medicine, Karolinska Institutet, Sweden. Rino Bellocco, Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden, and Department of Statistics, University of Milano Bicocca, Milan, Italy. Sander Greenland, Departments of Epidemiology and Statistics, University of California, Los Angeles, CA, U.S.A. Support

http://nicolaorsini.altervista.org nicola.orsini@ki.se